CN112367708B - Network resource allocation method and device - Google Patents
Network resource allocation method and device Download PDFInfo
- Publication number
- CN112367708B CN112367708B CN202011192969.5A CN202011192969A CN112367708B CN 112367708 B CN112367708 B CN 112367708B CN 202011192969 A CN202011192969 A CN 202011192969A CN 112367708 B CN112367708 B CN 112367708B
- Authority
- CN
- China
- Prior art keywords
- service
- target
- characteristic value
- transmission resources
- target service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/53—Allocation or scheduling criteria for wireless resources based on regulatory allocation policies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application provides a network resource allocation method and device, which can obtain a service characteristic value of a target service; and inputting the obtained service characteristic value into a trained neural network model to obtain transmission resources required by the transmission of the target service, and issuing the transmission resources to target equipment so that the target equipment can transmit the target service by using the transmission resources. Therefore, by applying the technical scheme provided by the embodiment of the application, the service forwarding efficiency can be improved on the basis of saving network resources.
Description
Technical Field
The present disclosure relates to the field of data transmission technologies, and in particular, to a method and an apparatus for allocating network resources.
Background
With the continuous development of the mobile internet, various novel applications such as cloud services, AR/VR and Internet of vehicles are continuously emerging, and a fifth generation mobile communication (5G) technology is developed for coping with the future explosive mobile data traffic growth and mass equipment connection. The FlexE (Flexible Ethernet ) technology is an important interface technology for implementing service isolation bearer and network fragmentation for a 5G bearer network by using characteristics of specific physical isolation, channel binding, single set mapping, and the like, and based on this, the FlexE is used to transmit data, which has: the multi-granularity rate is flexible and variable, is decoupled from the optical transmission capability, is oriented to the capabilities of enhancing QoS (quality of service) of multi-service bearing and the like, and is widely applied to metropolitan area network links such as cloud computing, video, mobile communication and the like.
However, flexE is allocated as a minimum granularity unit by time slot. In the prior art, corresponding time slots are allocated to the service to be forwarded in each router in a mode of manual static configuration of a command line, in practice, the traffic flow of the service is not fixed, in more cases, the actual occupied resources of the service do not reach the transmission resources allocated to the service, even differ more from the transmission resources allocated to the service, and the resources are wasted for the network resources of the size of land, and meanwhile, in the case of more routers, the efficiency of forwarding the service by the router is also low in the mode of manual static configuration of the command line.
Disclosure of Invention
In view of this, the present application provides a method and apparatus for allocating network resources, so as to improve service forwarding efficiency on the basis of saving network resources.
Specifically, the application is realized by the following technical scheme:
in one aspect, an embodiment of the present application provides a network resource allocation method, where the method is applied to a network device in an SDN network, and includes:
obtaining a service characteristic value of the target service;
and inputting the obtained service characteristic value into a trained neural network model to obtain transmission resources required by transmitting the target service, and transmitting the transmission resources to the target equipment so that the target equipment can transmit the target service by utilizing the transmission resources.
On the other hand, based on the same concept, the embodiment of the present application further provides a network resource allocation apparatus, where the apparatus is applied to a network device in an SDN network, including:
a feature value obtaining unit, configured to obtain a service feature value of the target service;
the transmission resource obtaining unit is used for inputting the obtained service characteristic value into the trained neural network model to obtain the transmission resource required by transmitting the target service, and transmitting the transmission resource to the target equipment so that the target equipment can transmit the target service by utilizing the transmission resource.
As can be seen from the above technical solutions, in the embodiments of the present application, transmission resources are allocated to a service in a manner of manual static configuration of a command line, but a network device of an SDN network inputs a service feature value of the service into a trained neural network model, dynamically obtains the transmission resources allocated to the service, and issues the obtained transmission resources to a device that receives the service, so that service forwarding efficiency can be improved on the basis of saving network resources.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a schematic flow chart of a network resource allocation method provided in the embodiment of the present application;
fig. 2 is a schematic flow chart of adjusting a service feature value according to an embodiment of the present application;
FIG. 3 is a flow chart of an exemplary video resource allocation provided by an embodiment of the present application;
fig. 4 is a schematic structural diagram of a network resource allocation device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The network device comprises a plurality of network devices, wherein the network devices can be SDN controllers and other network devices connected with the SDN controllers, and the network devices connected with the SDN controllers are communicated through a FlexE network.
In order to better understand the technical solution in the embodiments of the present invention and make the above objects, features and advantages of the embodiments of the present invention more comprehensible, the technical solution in the embodiments of the present invention is described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart of a network resource allocation method according to an embodiment of the present invention, where the method may be applied to a network device in an SDN (Software Defined Network ) network, and in an example, the network device may be an SDN controller, or may be another network device connected to the SDN controller, which is not particularly limited in this application.
As shown in fig. 1, the process may include the steps of:
and 101, obtaining a service characteristic value of the target service.
The target service does not refer to a fixed service, but may refer to a service to be transmitted by any network, which is not described in the embodiments of the present application.
Accordingly, the target device may be any device in an SDN network for forwarding target traffic, such as a router and a switch.
When receiving a target service needing to be forwarded, the target device does not determine how many transmission resources need to be allocated to the target service to perform network transmission on the target service, and based on the determination, as an embodiment: the target device may send a resource allocation request to the network device to cause the network resource to send the transmission resource allocated for the target service for the target device.
Some behavior characteristics of the service in the network transmission process imply transmission resources required by the service in network transmission, and the behavior characteristics are service characteristic values of the service. As an embodiment, the service characteristic value of the target service may include any combination of the following characteristic values: occupied bandwidth, occupied duration, total data volume, traffic type, burst traffic, latency, and ACK (Acknowledge character, acknowledgement character) information.
The input information of the trained neural network model is a service characteristic value of a service, and the output information is transmission resources required for transmitting the service.
In the application, the trained neural network model can dynamically estimate the transmission resources required by the service according to the service characteristic value of the service at the current moment.
The transmission resources may include at least: time slots, bandwidths or durations.
As one example, the neural network model may be trained by:
obtaining sample service characteristic values corresponding to services of different service categories;
and training the neural network model according to the configured sample service characteristic values and sample transmission resources corresponding to the sample service characteristic values.
In this embodiment, the sample service characteristic value is a service characteristic value of a service of a different service class.
And taking the sample service characteristic value as input information of the neural network model, and taking a sample transmission resource corresponding to the sample service characteristic value as a training reference to train the neural network model.
Therefore, in the technical scheme provided by the embodiment of the application, the sample service characteristic values corresponding to the services of different service types are abundant and comprehensive, so that the trained neural network model can accurately predict the transmission resources of the services.
Therefore, in the technical solution provided in the embodiment of the present application, transmission resources are not allocated to the service by using a mode of manual static configuration of the command line, but when the target device receives the service to be forwarded, the network device of the SDN network inputs the service feature value of the service into the trained neural network model, dynamically obtains the transmission resources allocated to the service, and issues the transmission resources to the target device, so that the service forwarding efficiency can be improved on the basis of saving the network resources.
Thus, the flow shown in fig. 1 is completed.
In the flow shown in fig. 1, as an embodiment, before executing the flow shown in fig. 1, the target device first receives the target service to be forwarded, and on the premise that the target device receives the target service to be forwarded, the network device executes steps 101 to 102 described above, so that after the network device issues the predicted transmission resource to the target device, the target service is forwarded quickly.
As another embodiment, before executing the flow shown in fig. 1, the network manager (or the operation and maintenance personnel) receives the target service to be forwarded by the service department (or the customer), and the network manager inputs the service characteristic value of the target service in the network device, and on the premise that the network device executes the steps 101 to 102, so that after the network device issues the predicted transmission resource to the target device, the target service can be forwarded quickly when the target device receives the target service to be forwarded, thereby further improving the service forwarding efficiency.
In the flow shown in fig. 1, there are many implementation manners of step 101, which may include at least the following six implementation manners, specifically:
the first implementation mode: and obtaining a first type of characteristic value of the target service input from the outside, and determining the first type of characteristic value as the service characteristic value of the target service.
Aiming at the fact that more service feature values exist and the user manually inputs the feature values, the burden of the user may be increased and the service forwarding efficiency is affected, the specific implementation manner of step 101 may be as follows:
the second implementation mode: and searching a second type of characteristic value associated with the first type of characteristic value from the configured characteristic value list, and determining the second type of characteristic value as a service characteristic value of the target service.
The technical scheme provided by the second implementation mode can be used for reducing the manpower burden and correspondingly reducing the human error rate.
In order to reduce the artificial burden, and dynamically obtain the real service characteristic value of the service more realistically, the specific implementation manner of step 101 may be:
the third implementation mode is as follows: and receiving a third class characteristic value of the target service, which is obtained by analyzing the target service, by the target device, and determining the third class characteristic value as the service characteristic value of the target service.
According to the technical scheme provided by the third implementation mode, the implementation mode can not only reduce the labor burden, but also reduce the artificial error rate, and can also improve the accuracy of distributing transmission resources for the service.
For the case that the traffic data of some services are not fixed and there are more service feature values of the services, the specific implementation manner of step 101 may be:
the fourth implementation manner is as follows: the method comprises the steps of obtaining a first type of characteristic value of a target service input from the outside, searching a second type of characteristic value associated with the first type of characteristic value from a configured characteristic value list, and determining the first type of characteristic value and the second type of characteristic value as service characteristic values of the target service.
The first type of characteristic value may be a characteristic value that the user inputs according to an actual experience value, where the influence on the transmission resource of the target service is greater, for example, the first type of characteristic value may be an estimated occupied bandwidth of the target service, or may be a service class of the target service.
The second type of feature values may be feature values that have a smaller influence on the transmission resources of the target service, which are determined by the user according to actual experience values, and based on the feature values, after determining the first type of feature values, the second type of feature values may be configured in advance according to the first type of feature values. As an embodiment, a specific implementation manner of searching the second type of feature values associated with the first type of feature values from the configured feature value list may be: obtaining a first type characteristic value of an externally input target service; and determining a second type of characteristic values corresponding to the characteristic value range to which the first type of characteristic values belong from the configured characteristic value list.
For example, assuming that the first type of feature value obtained by external input is a fixed bandwidth 50G and the service class is video, from the configured feature value list, determining the video class of the fixed bandwidth 50G in the range of 40G-80G, wherein the second type of feature value corresponding to the video class in the range of 40G-80G is 100G of total data amount, and the occupied time period is 20 minutes.
The technical scheme provided by the fourth implementation mode can be seen that the implementation mode not only can reduce the labor burden, but also can flexibly set the first type of characteristic values and the second type of characteristic values according to the characteristics of the service so as to ensure the accuracy of the service characteristic values.
For some service feature values, there may be target devices that cannot obtain the service feature values by parsing the service, and for this reason, the specific implementation of step 101 may be:
the fifth implementation manner is as follows: the method comprises the steps of obtaining a first type of characteristic value of an externally input target service, receiving a third type of characteristic value of the target service, which is obtained by analyzing the target service by target equipment, and determining the first type of characteristic value and the third type of characteristic value as service characteristic values of the target service.
The third class of feature values is obtained by analyzing the target service by the target device, for example, determining the service class of the target service and the total data amount of the target service by analyzing the target service.
The technical scheme provided by the fifth implementation manner can be seen that the implementation manner not only can reduce the labor burden, but also can obtain the real service characteristic value of the service through the target equipment, so that the first type characteristic value and the third type characteristic value are flexibly set, and the accuracy of the service characteristic value can be further ensured.
Based on the descriptions of the first to fifth implementation manners, in order to obtain a richer and comprehensive service feature value, the specific implementation manner of step 101 may further be:
the sixth implementation manner is as follows: the method comprises the steps of obtaining a first type of characteristic value of an externally input target service, searching a second type of characteristic value associated with the first type of characteristic value from a configured characteristic value list, receiving a third type of characteristic value of the target service obtained by analyzing the target service by target equipment, and determining the second type of characteristic value and the third type of characteristic value as service characteristic values of the target service.
In this implementation manner, the first type of feature value may be a feature value that the user inputs, according to an actual experience value, a feature value that has a large influence on a transmission resource of the target service and cannot be obtained from the target device, the second type of feature value may be a feature value that has a small influence on the transmission resource of the target service and cannot be obtained from the target device, which is determined by the user according to the actual experience value, and the third type of feature value is a feature value obtained by analyzing the target service through the target device.
In the technical scheme provided by the sixth implementation manner, not only the burden brought by the input service characteristic value to the human force can be reduced, but also the real characteristic value of the service can be obtained through the target equipment, so that the obtained service characteristic value is rich and comprehensive, and the accuracy of the service characteristic value can be further ensured.
Referring to fig. 2, fig. 2 is a flowchart of a further exemplary embodiment based on implementation of various specific implementations of step 101 described above according to embodiments of the present application. As shown in fig. 2, the process may include the steps of:
In this step, the transmission resources actually occupied when the target service is obtained may include two cases:
the first case is: the transmission resources actually occupied when transmitting the target service are larger than the transmission resources issued to the target device by the network device in step 102.
The second case is: the transmission resources actually occupied when transmitting the target service are smaller than the transmission resources issued to the target device.
Based on the two cases, as an embodiment, the implementation manner of implementing step 201 may include the following steps:
if the transmission resources of the issuing target equipment are all occupied, determining the transmission resources actually occupied by the target service according to the transmission characteristics of the target service.
In this step, the transmission resources issued to the target device are fully occupied, which means that the first situation is met. That is, when the transmission resource actually occupied when transmitting the target service is greater than the transmission resource actually occupied by the network device and issued to the target device, there may be a transmission characteristic of packet loss and broken code, based on this, as an embodiment, the packet loss rate or the broken code rate of the target service may be counted, and then the transmission resource lost by the target service, and further the transmission resource actually occupied by the target service and the transmission resource lost by the target service are determined according to the counted value, so as to determine the transmission resource actually occupied by the target service.
In addition, for the first case, as an embodiment, after determining the transmission resource actually occupied by the target service, the actually occupied transmission resource may be reported, so as to confirm whether to further increase the transmission resource by the standby user.
And if the transmission resources issued to the target equipment are not fully occupied, acquiring the transmission resources actually occupied by the target equipment for transmitting the target service from the target equipment.
In this step, the transmission resources issued to the target device are fully occupied, which means that the second situation is met.
As an embodiment, in the case that it is determined that the ratio of the transmission resource actually occupied by the transmission target service to the transmission resource issued to the target device is greater than the threshold, the transmission resource actually occupied by the transmission target service may be reported, so as to trigger the present network device to execute step 202.
For the first case, based on the above embodiment, if the user determines to increase the transmission resources, the service feature value of the target service may be readjusted according to the transmission resources actually occupied by the reported target service.
When the service characteristic value is obtained through the first implementation manner, the first type of characteristic value is adjusted according to the transmission resource actually occupied by the obtained target equipment when transmitting the target service.
And when the service characteristic value is obtained through the second implementation mode, adjusting the second type characteristic value according to the transmission resources actually occupied by the obtained target equipment when transmitting the target service.
When the service characteristic value is obtained through the fourth implementation manner, the fifth implementation manner or the sixth implementation manner, the first type characteristic value and the second type characteristic value are adjusted according to the transmission resources actually occupied when the obtained target equipment transmits the target service.
Therefore, in the technical solution of the embodiment of the present application, the embodiment adjusts the service characteristic value according to the transmission resource actually occupied when the target device transmits the target service, so that when the target device receives the service needing to be forwarded next time, the network device of the SDN network inputs the adjusted service characteristic value of the service into the trained neural network model, dynamically obtains the transmission resource allocated for the service, and issues the transmission resource to the target device, so that the transmission resource issued to the target device more accords with the transmission resource actually occupied when the target service is transmitted, and further saves the network resource.
Thus, the flow shown in fig. 2 is completed.
Referring to fig. 3, an architecture schematic diagram of an application scenario provided in this embodiment of the present application is shown in fig. 3, where a network resource is provided with 2 calendars, 1 calendar has 20 timeslots, and 1 timeslot is a small rectangle in fig. 3, in this application scenario, a target device is a router, a target service received by the router is a video service, in this embodiment, a network device applied to an SDN network may be an SDN controller, and a specific flow of this embodiment is as follows:
firstly, a network manager receives a new video service to be added by a service department (or a client), the network manager inputs the fixed bandwidth and the service type of the video service into an interactive interface of an SDN controller, the SDN controller obtains the fixed bandwidth and the service type input by a user, searches occupation time duration, time delay and ACK information associated with the obtained fixed bandwidth and service type from a configured characteristic value list, and a router through which the video service is routed subsequently determines that the service characteristic value of the video is occupation bandwidth, occupation time duration, total data volume, service type, burst flow, time delay and ACK information by analyzing the total data volume and the burst flow of the video.
And secondly, inputting the service characteristic value obtained in the first step into a trained neural network model to obtain 5 time slots required for transmitting the video, such as A, B, C, D and E in fig. 3, and transmitting the 5 time slots to the router, wherein when the router receives the newly added video service, the router can transmit the video by using the 5 time slots, and after the time slots are distributed, the video can be transmitted in the 5 time slots.
As can be seen from fig. 3, the router, upon receiving the 5 slots A, B, C, D and E, forwards the video in sequence in the order of the 5 slots.
And thirdly, in the forwarding process, if all the 5 time slots of the router are occupied, indicating that the bandwidth actually occupied by the video is more than 5 time slots, wherein the situations of packet loss, congestion and the like already occur, determining the time slots actually occupied by the video according to the transmission characteristics of the packet loss rate, the code breaking rate and the like of the video service based on the situations, and reporting the network actual state, namely the time slots actually occupied by the video.
If the 5 time slots of the routing router are not fully occupied (e.g., a large number of error process blocks occur in the time slots, i.e., error Control Block is filled), the time slots representing the actual occupation of the video are less than 5 time slots, and the transmission resources actually occupied by the router when transmitting the video are obtained from the router.
And step four, according to the time slot actually occupied by the router when transmitting the video, which is obtained in the step three, the fixed bandwidth and the service type are adjusted, the occupied time length, the time delay and the ACK information which are associated with the adjusted fixed bandwidth and the adjusted service type are searched from the configured characteristic value list, the adjusted fixed bandwidth, the adjusted service type, the occupied time length, the time delay and the ACK information, and the total data volume and the burst flow which are obtained by analyzing the video from the router are determined as the service characteristic value of the next video.
The examples provided herein were analyzed above.
Based on the same application concept as the above method, the embodiment of the present application further provides a network resource allocation apparatus 400, where the apparatus is applied to a network device in an SDN network, as shown in fig. 4, and is a structural diagram of the apparatus, and the apparatus includes:
a feature value obtaining unit 401, configured to obtain a service feature value of the target service.
And a transmission resource obtaining unit 402, configured to input the obtained service characteristic value into a trained neural network model, obtain a transmission resource required for transmitting the target service, and issue the transmission resource to the target device, so that the target device uses the transmission resource to transmit the target service.
As one embodiment, the feature value obtaining unit 401 may include:
a first class feature value obtaining subunit, configured to obtain a first class feature value of an externally input target service; and/or the number of the groups of groups,
a second-class feature value obtaining subunit, configured to find a second-class feature value associated with the first-class feature value from a configured feature value list; and/or the number of the groups of groups,
a third class feature value obtaining subunit, configured to receive a third class feature value of the target service, where the third class feature value is obtained by analyzing the target service by the target device;
and the characteristic value determining subunit is used for determining the first type characteristic value and/or the second type characteristic value and/or the third type characteristic value as the service characteristic value of the target service.
As an embodiment, the apparatus may further include:
a transmission resource obtaining unit, configured to obtain a transmission resource actually occupied by the target device when transmitting the target service;
and the characteristic value adjusting unit is used for adjusting the first type characteristic value and/or the second type characteristic value according to the obtained transmission resources actually occupied by the target equipment when transmitting the target service.
As an embodiment, the transmission resource obtaining unit is specifically configured to:
if the transmission resources issued to the target equipment are all occupied, determining the transmission resources actually occupied by the target service according to the transmission characteristics of the target service;
and if the transmission resources issued to the target equipment are not fully occupied, acquiring the transmission resources actually occupied by the target equipment when the target equipment transmits the target service from the target equipment.
As an embodiment, the apparatus may further include: the model training unit is used for training a neural network model;
the model training unit is specifically configured to:
obtaining sample service characteristic values corresponding to services of different service categories;
and training the neural network model according to the configured sample service characteristic values and sample transmission resources corresponding to the sample service characteristic values.
As an embodiment, the service characteristic value of the target service may include any combination of the following characteristic values:
occupied bandwidth, occupied duration, total data volume, traffic type, burst traffic, delay and ACK information.
As an embodiment, the transmission resources at least include: time slot, bandwidth, and duration.
In summary, in the technical solution provided in the embodiment of the present application, transmission resources are allocated to a service in a manner of manual static configuration of a command line, but network devices of an SDN network input service feature values of the service into a trained neural network model, the transmission resources allocated to the service are dynamically obtained, and the obtained transmission resources are issued to devices receiving the service, so that service forwarding efficiency can be improved on the basis of saving network resources.
The implementation process of the functions and roles of each unit in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
In the electronic device provided in the embodiment of the present application, from a hardware level, a schematic diagram of a hardware architecture may be shown in fig. 5. Comprising the following steps: a machine-readable storage medium and a processor, wherein: the machine-readable storage medium stores machine-executable instructions executable by the processor; the processor is configured to execute the machine-executable instructions to implement the network resource allocation operations disclosed in the examples above.
Machine-readable storage media provided by embodiments of the present application store machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the network resource allocation operations disclosed by the above examples.
Here, a machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that may contain or store information, such as executable instructions, data, or the like. For example, a machine-readable storage medium may be: RAM (Radom Access Memory, random access memory), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., hard drive), a solid state drive, any type of storage disk (e.g., optical disk, dvd, etc.), or a similar storage medium, or a combination thereof.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Moreover, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A network resource allocation method, wherein the method is applied to network equipment in an SDN network, and comprises:
obtaining a first type characteristic value of an externally input target service;
searching a second type of characteristic value associated with the first type of characteristic value from a configured characteristic value list;
receiving a third type characteristic value of the target service, which is obtained by analyzing the target service by target equipment;
determining the first class characteristic value or the second class characteristic value and the third class characteristic value as service characteristic values of the target service;
inputting the obtained service characteristic value into a trained neural network model to obtain transmission resources required by transmitting the target service, and transmitting the transmission resources to the target equipment so that the target equipment can transmit the target service by utilizing the transmission resources;
acquiring transmission resources actually occupied by the target equipment when transmitting the target service;
and adjusting the first type characteristic value and/or the second type characteristic value according to the obtained transmission resources actually occupied when the target equipment transmits the target service.
2. The method according to claim 1, wherein the obtaining transmission resources actually occupied by the target device when transmitting the target service includes:
if the transmission resources issued to the target equipment are all occupied, determining the transmission resources actually occupied by the target service according to the transmission characteristics of the target service;
and if the transmission resources issued to the target equipment are not fully occupied, acquiring the transmission resources actually occupied by the target equipment when transmitting the target service from the target equipment.
3. The method of claim 1, wherein the neural network model is trained by:
obtaining sample service characteristic values corresponding to services of different service categories;
and training the neural network model according to the configured sample service characteristic values and sample transmission resources corresponding to the sample service characteristic values.
4. The method of claim 1, wherein the traffic characteristic values of the target traffic include any combination of the following characteristic values:
occupied bandwidth, occupied duration, total data volume, traffic type, burst traffic, delay and ACK information.
5. The method according to claim 1, wherein the transmission resources comprise at least: time slot, bandwidth, and duration.
6. A network resource allocation apparatus, wherein the apparatus is applied to a network device in an SDN network, and comprises:
the characteristic value obtaining unit is used for obtaining a first type characteristic value of the target service input from the outside;
searching a second type of characteristic value associated with the first type of characteristic value from a configured characteristic value list;
receiving a third type characteristic value of the target service, which is obtained by analyzing the target service by target equipment;
determining the first class characteristic value or the second class characteristic value and the third class characteristic value as service characteristic values of the target service;
a transmission resource obtaining unit, configured to input the obtained service feature value into a trained neural network model, obtain a transmission resource required for transmitting the target service, and issue the transmission resource to the target device, so that the target device uses the transmission resource to transmit the target service;
acquiring transmission resources actually occupied by the target equipment when transmitting the target service;
and adjusting the first type characteristic value and/or the second type characteristic value according to the obtained transmission resources actually occupied when the target equipment transmits the target service.
7. The apparatus according to claim 6, wherein the transmission resource obtaining unit is specifically configured to:
if the transmission resources issued by the target equipment are detected to be fully occupied, determining the transmission resources actually occupied by the target service according to the transmission characteristics of the target service;
and if the transmission resources issued by the target equipment are detected not to be fully occupied, acquiring the transmission resources actually occupied by the target equipment when the target equipment transmits the target service from the target equipment.
8. The apparatus of claim 6, wherein the apparatus further comprises: the model training unit is used for training a neural network model;
the model training unit is specifically configured to:
obtaining sample service characteristic values corresponding to services of different service categories;
and training the neural network model according to the configured sample service characteristic values and sample transmission resources corresponding to the sample service characteristic values.
9. The apparatus of claim 6, wherein the traffic characteristic values of the target traffic comprise any combination of the following characteristic values:
occupied bandwidth, occupied duration, total data volume, traffic type, burst traffic, delay and ACK information.
10. The apparatus of claim 6, wherein the transmission resources comprise at least: time slot, bandwidth, and duration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011192969.5A CN112367708B (en) | 2020-10-30 | 2020-10-30 | Network resource allocation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011192969.5A CN112367708B (en) | 2020-10-30 | 2020-10-30 | Network resource allocation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112367708A CN112367708A (en) | 2021-02-12 |
| CN112367708B true CN112367708B (en) | 2023-05-26 |
Family
ID=74513315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011192969.5A Active CN112367708B (en) | 2020-10-30 | 2020-10-30 | Network resource allocation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112367708B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114339772B (en) * | 2021-11-19 | 2023-04-07 | 煤炭科学技术研究院有限公司 | Resource allocation method and device and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104507126A (en) * | 2014-11-21 | 2015-04-08 | 中兴通讯股份有限公司 | Method and device for implementing wireless network QoS (Quality of Service) management |
| CN108449286A (en) * | 2018-03-01 | 2018-08-24 | 北京邮电大学 | Method and device for allocating network bandwidth resources |
| CN109756911A (en) * | 2019-01-31 | 2019-05-14 | 腾讯科技（深圳）有限公司 | Network quality prediction technique, business reorganization method, relevant device and storage medium |
| CN109857518A (en) * | 2019-01-08 | 2019-06-07 | 平安科技（深圳）有限公司 | A kind of distribution method and equipment of Internet resources |
| CN110912736A (en) * | 2019-11-13 | 2020-03-24 | 中国联合网络通信集团有限公司 | Resource allocation method and device |
| CN111107651A (en) * | 2019-12-27 | 2020-05-05 | 中国联合网络通信集团有限公司 | Method and device for scheduling wireless resources |
| CN111491312A (en) * | 2019-01-28 | 2020-08-04 | 中国移动通信有限公司研究院 | Method and equipment for predicting, allocating, acquiring and training neural network of wireless resources |
| CN111711538A (en) * | 2020-06-08 | 2020-09-25 | 中国电力科学研究院有限公司 | Power network planning method and system based on machine learning classification algorithm |
-
2020
- 2020-10-30 CN CN202011192969.5A patent/CN112367708B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104507126A (en) * | 2014-11-21 | 2015-04-08 | 中兴通讯股份有限公司 | Method and device for implementing wireless network QoS (Quality of Service) management |
| CN108449286A (en) * | 2018-03-01 | 2018-08-24 | 北京邮电大学 | Method and device for allocating network bandwidth resources |
| CN109857518A (en) * | 2019-01-08 | 2019-06-07 | 平安科技（深圳）有限公司 | A kind of distribution method and equipment of Internet resources |
| CN111491312A (en) * | 2019-01-28 | 2020-08-04 | 中国移动通信有限公司研究院 | Method and equipment for predicting, allocating, acquiring and training neural network of wireless resources |
| CN109756911A (en) * | 2019-01-31 | 2019-05-14 | 腾讯科技（深圳）有限公司 | Network quality prediction technique, business reorganization method, relevant device and storage medium |
| CN110912736A (en) * | 2019-11-13 | 2020-03-24 | 中国联合网络通信集团有限公司 | Resource allocation method and device |
| CN111107651A (en) * | 2019-12-27 | 2020-05-05 | 中国联合网络通信集团有限公司 | Method and device for scheduling wireless resources |
| CN111711538A (en) * | 2020-06-08 | 2020-09-25 | 中国电力科学研究院有限公司 | Power network planning method and system based on machine learning classification algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 基于群集运动智能的SDN业务传输优化技术;周宁等;《重庆邮电大学学报(自然科学版)》;20190615(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112367708A (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111512602B (en) | Method, equipment and system for sending message | |
| US11165705B2 (en) | Data transmission method, device, and computer storage medium | |
| US9509620B2 (en) | Deadline-aware network protocol | |
| CN117880092A (en) | Network parameter configuration method, device, computer equipment and storage medium | |
| EP4075732A1 (en) | Service level configuration method and device | |
| CN112367708B (en) | Network resource allocation method and device | |
| CN112714081B (en) | Data processing method and device | |
| EP3582455A1 (en) | Method and apparatus for multiple sub-current network transmission | |
| US8693328B2 (en) | Method and apparatus for distributing credits to multiple shapers to enable shaping traffic targets in packet communication networks | |
| CN114070798B (en) | Message transmission method, device and equipment | |
| CN115695523A (en) | Data transmission control method and device, electronic equipment and storage medium | |
| CN112005528B (en) | Data exchange method, data exchange node and data center network | |
| CN109995608B (en) | Network rate calculation method and device | |
| CN113453285B (en) | Resource adjusting method, device and storage medium | |
| CN114157604B (en) | Method, device and system for adjusting congestion of switching network board | |
| CN114024913B (en) | Network performance optimization method, device, equipment and storage medium | |
| US11012378B2 (en) | Methods and apparatus for shared buffer allocation in a transport node | |
| CN113852554B (en) | Data transmission method, device and equipment | |
| CN107371263B (en) | Method and device for scheduling uplink resources | |
| KR101681613B1 (en) | Apparatus and method for scheduling resources in distributed parallel data transmission system | |
| US9871733B2 (en) | Policer architecture | |
| CN110336758B (en) | Data distribution method in virtual router and virtual router | |
| CN110933135B (en) | Method and apparatus for establishing network connection in computer device | |
| CN107800516B (en) | Method and device for high-speed downlink packet access (HSDPA) storage management | |
| US8031721B2 (en) | Method and apparatus for marking and scheduling packets for transmission |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |